phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 18:54:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(caching.py): support s-maxage param for cache controls

Browse source
This commit is contained in:
Krrish Dholakia 2024-01-04 11:41:23 +05:30
parent 4946b1ef6d
commit b0827a87b2
3 changed files with 13 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

8
litellm/caching.py
View file

@ -11,6 +11,7 @@ import litellm
import time, logging
import json, traceback, ast, hashlib
from typing import Optional, Literal, List, Union, Any
from openai._models import BaseModel as OpenAIObject
def print_verbose(print_statement):
@ -472,7 +473,10 @@ class Cache:
else:
cache_key = self.get_cache_key(*args, **kwargs)
if cache_key is not None:
max_age = kwargs.get("cache", {}).get("s-max-age", float("inf"))
cache_control_args = kwargs.get("cache", {})
max_age = cache_control_args.get(
"s-max-age", cache_control_args.get("s-maxage", float("inf"))
)
cached_result = self.cache.get_cache(cache_key)
# Check if a timestamp was stored with the cached response
if (
@ -529,7 +533,7 @@ class Cache:
else:
cache_key = self.get_cache_key(*args, **kwargs)
if cache_key is not None:
if isinstance(result, litellm.ModelResponse):
if isinstance(result, OpenAIObject):
result = result.model_dump_json()
## Get Cache-Controls ##